video-speed-api

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to store the API key in a hidden directory and set restricted permissions using chmod 600, which is a secure method for local credential storage.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and additional assets from the vendor's official domains (pixazo.ai and pixazo-assets.pixazo.ai), which is expected behavior.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts and external video URLs, which represents a potential surface for indirect prompt injection. Ingestion points: video_url and user prompt in SKILL.md instructions. Boundary markers: None identified. Capability inventory: Network requests via curl and requests.post in SKILL.md. Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:02 PM